Matches in SemOpenAlex for { <https://semopenalex.org/work/W3135890227> ?p ?o ?g. }
- W3135890227 abstract "Machine learning models trained on imbalanced datasets can often end up adversely affecting inputs belonging to the underrepresented groups. To address this issue, we consider the problem of adaptively constructing training sets which allow us to learn classifiers that are fair in a minimax sense. We first propose an adaptive sampling algorithm based on the principle of optimism, and derive theoretical bounds on its performance. We then suitably adapt the techniques developed for the analysis of our proposed algorithm to derive bounds on the performance of a related $epsilon$-greedy strategy recently proposed in the literature. Next, by deriving algorithm independent lower-bounds for a specific class of problems, we show that the performance achieved by our adaptive scheme cannot be improved in general. We then validate the benefits of adaptively constructing training sets via experiments on synthetic tasks with logistic regression classifiers, as well as on several real-world tasks using convolutional neural networks." @default.
- W3135890227 created "2021-03-15" @default.
- W3135890227 creator A5013843778 @default.
- W3135890227 creator A5059310658 @default.
- W3135890227 creator A5061321764 @default.
- W3135890227 date "2021-03-01" @default.
- W3135890227 modified "2023-10-16" @default.
- W3135890227 title "Adaptive Sampling for Minimax Fair Classification." @default.
- W3135890227 cites W2014352947 @default.
- W3135890227 cites W2100960835 @default.
- W3135890227 cites W2124379907 @default.
- W3135890227 cites W2135664069 @default.
- W3135890227 cites W2153015072 @default.
- W3135890227 cites W2162670686 @default.
- W3135890227 cites W2168405694 @default.
- W3135890227 cites W2318680928 @default.
- W3135890227 cites W2530395818 @default.
- W3135890227 cites W2592232824 @default.
- W3135890227 cites W2750384547 @default.
- W3135890227 cites W2912457762 @default.
- W3135890227 cites W2946016480 @default.
- W3135890227 cites W2963327716 @default.
- W3135890227 cites W2963741226 @default.
- W3135890227 cites W2964256806 @default.
- W3135890227 cites W2999380901 @default.
- W3135890227 cites W3013451997 @default.
- W3135890227 cites W3034396216 @default.
- W3135890227 cites W3034460046 @default.
- W3135890227 cites W3034879135 @default.
- W3135890227 cites W3092541244 @default.
- W3135890227 cites W3100279624 @default.
- W3135890227 cites W3118608800 @default.
- W3135890227 cites W3123374861 @default.
- W3135890227 cites W3134893036 @default.
- W3135890227 cites W3154300329 @default.
- W3135890227 hasPublicationYear "2021" @default.
- W3135890227 type Work @default.
- W3135890227 sameAs 3135890227 @default.
- W3135890227 citedByCount "1" @default.
- W3135890227 countsByYear W31358902272020 @default.
- W3135890227 crossrefType "posted-content" @default.
- W3135890227 hasAuthorship W3135890227A5013843778 @default.
- W3135890227 hasAuthorship W3135890227A5059310658 @default.
- W3135890227 hasAuthorship W3135890227A5061321764 @default.
- W3135890227 hasConcept C105795698 @default.
- W3135890227 hasConcept C106131492 @default.
- W3135890227 hasConcept C11413529 @default.
- W3135890227 hasConcept C119857082 @default.
- W3135890227 hasConcept C126255220 @default.
- W3135890227 hasConcept C134306372 @default.
- W3135890227 hasConcept C140779682 @default.
- W3135890227 hasConcept C149728462 @default.
- W3135890227 hasConcept C154945302 @default.
- W3135890227 hasConcept C19499675 @default.
- W3135890227 hasConcept C2777212361 @default.
- W3135890227 hasConcept C2781395549 @default.
- W3135890227 hasConcept C31972630 @default.
- W3135890227 hasConcept C33923547 @default.
- W3135890227 hasConcept C41008148 @default.
- W3135890227 hasConcept C77618280 @default.
- W3135890227 hasConceptScore W3135890227C105795698 @default.
- W3135890227 hasConceptScore W3135890227C106131492 @default.
- W3135890227 hasConceptScore W3135890227C11413529 @default.
- W3135890227 hasConceptScore W3135890227C119857082 @default.
- W3135890227 hasConceptScore W3135890227C126255220 @default.
- W3135890227 hasConceptScore W3135890227C134306372 @default.
- W3135890227 hasConceptScore W3135890227C140779682 @default.
- W3135890227 hasConceptScore W3135890227C149728462 @default.
- W3135890227 hasConceptScore W3135890227C154945302 @default.
- W3135890227 hasConceptScore W3135890227C19499675 @default.
- W3135890227 hasConceptScore W3135890227C2777212361 @default.
- W3135890227 hasConceptScore W3135890227C2781395549 @default.
- W3135890227 hasConceptScore W3135890227C31972630 @default.
- W3135890227 hasConceptScore W3135890227C33923547 @default.
- W3135890227 hasConceptScore W3135890227C41008148 @default.
- W3135890227 hasConceptScore W3135890227C77618280 @default.
- W3135890227 hasOpenAccess W3135890227 @default.
- W3135890227 hasRelatedWork W1499247608 @default.
- W3135890227 hasRelatedWork W1714704734 @default.
- W3135890227 hasRelatedWork W2112008717 @default.
- W3135890227 hasRelatedWork W2244118489 @default.
- W3135890227 hasRelatedWork W2284172031 @default.
- W3135890227 hasRelatedWork W258707964 @default.
- W3135890227 hasRelatedWork W2886611740 @default.
- W3135890227 hasRelatedWork W2891124631 @default.
- W3135890227 hasRelatedWork W2963147615 @default.
- W3135890227 hasRelatedWork W2964276957 @default.
- W3135890227 hasRelatedWork W2989980396 @default.
- W3135890227 hasRelatedWork W2997227310 @default.
- W3135890227 hasRelatedWork W3012998781 @default.
- W3135890227 hasRelatedWork W3015121100 @default.
- W3135890227 hasRelatedWork W3023175709 @default.
- W3135890227 hasRelatedWork W3029655606 @default.
- W3135890227 hasRelatedWork W3111062593 @default.
- W3135890227 hasRelatedWork W3113682753 @default.
- W3135890227 hasRelatedWork W3204652201 @default.
- W3135890227 hasRelatedWork W327359575 @default.
- W3135890227 isParatext "false" @default.
- W3135890227 isRetracted "false" @default.
- W3135890227 magId "3135890227" @default.